---

deep learning lectures

Google Colab notebooks and sample datasets for the intensive Crash Course in Deep Learning, at Kaunas University of Applied Sciences, Lithuania

1. Python tutorials

This section offers 3 tutorials to familiarize with some basic libraries in Python:

• tutorial_1_numpy.ipynb
• tutorial_1_pandas.ipynb
• tutorial_1_matplotlib.ipynb

2. Artificial Neural Networks (ANNs)

In this notebook you will be tasked to solve a churn prediction problem using an artificial neural network classifier. The purpose of this study is to showcase how to:

• interrogate your data and apply basic data preprocessing methods for optimizing your tables;
• create a custom neural network classifier using Keras;
• train and deploy the ANN
• evaluate the model performance
• optimize/fine-tune the model

The code is available in artificial_neural_networks.ipynb.

3. Convolutional Neural Networks (CNNs)

shortly

4. Recurrent Neural Networks (RNNs)

In this notebook you will be tasked to solve a stock price prediction problem using recurrent neural networks. The purpose of this study is to showcase how to:

• obtain finacial data (stock prices),
• import it into dataframes and organize the later by filtering our redundant columns,
• transform the input data into meaningful feature vectors,
• create a custom reccurent neural network regressor using Keras,
• train and deploy the RNN,
• evaluate the model performance,
• optimize/fine-tune the model.

The code is available in recurrent_neural_networks.ipynb

Enjoy

Contact

Contact the author